mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-10-06 00:57:33 +08:00

* nvjpeg cmake * add common decoder, nvjpeg decoder and add image name predict api * ppclas support nvjpeg decoder * remove useless comments * image decoder support opencv * nvjpeg decode fallback to opencv * fdtensor add nbytes_allocated * single image decode api * fix bug * add pybind * ignore nvjpeg on jetson * fix cmake in * predict on fdmat * remove image names predict api, add image decoder tutorial * Update __init__.py * fix pybind
17 lines
346 B
Markdown
17 lines
346 B
Markdown
English | [中文](README_CN.md)
|
||
|
||
# Image Decoder
|
||
|
||
Currently, we support below image decoder libs:
|
||
- OpenCV
|
||
- nvJPEG (Needs NVIDIA GPU, doesn't support Jetson)
|
||
|
||
## Example
|
||
|
||
- [C++ Example](cpp)
|
||
- Python API(WIP)
|
||
|
||
## nvJPEG vs. OpenCV performance benchmark
|
||
|
||
Refer to: https://github.com/PaddlePaddle/FastDeploy/pull/1288#issuecomment-1427749772
|